Methods and apparatus to group advertisements by advertisement campaign

Abstract

Methods and apparatus to group advertisements by advertisement campaign are disclosed. An example apparatus includes memory; instructions in the apparatus; and processor circuitry to execute the instructions to determine pixel color values from a reference advertisement of an advertisement campaign; remove bits from the pixel color values associated with the reference advertisement; determine a first color proportion corresponding the reference advertisement based on the pixel color values; associate the first color proportion with the advertisement campaign; and identify a second advertisement as associated with the advertisement campaign based on a second color proportion of the second advertisement relative to the first color proportion, the second advertisement different than the reference advertisement.

What is claimed is: 
     
       1. A computing system comprising a processor and a memory, the computing system configured to perform a set of acts comprising:
 obtaining, by a server, a first candidate advertisement image and a second candidate advertisement image, different than the first candidate advertisement image; 
 determining red green blue (RGB) pixel color values of the first candidate advertisement image and RGB pixel color values of the second candidate advertisement image,
 wherein the server analyzes a first plurality of pixels of the first candidate advertisement image to determine the RGB pixel color value for each pixel of the first plurality of pixels of the first candidate advertisement image and a second plurality of pixels of the second candidate advertisement image to determine the RGB pixel color value for each pixel of the second plurality of pixels; 
 
 determining, based on the RGB pixel color values, a first color value of a top color proportion for the first candidate advertisement image and a second color value of a top color proportion for the second candidate advertisement image; 
 determining that the first color value of the top color proportion for the first candidate advertisement image is within a color range threshold of a color value of a reference color proportion of an advertisement campaign; 
 determining that the second color value of the top color proportion for the second candidate advertisement image is within the color range threshold of the color value of the reference color proportion of the advertisement campaign; 
 based on determining that the first color value of the top color proportion for the first candidate advertisement image is within the color range threshold of the color value of reference color proportion, associating the first candidate advertisement image with the advertisement campaign; and 
 based on determining that the second color value of the top color proportion for the second candidate advertisement image is within the color range threshold of the color value of reference color proportion, associating the second candidate advertisement image with the advertisement campaign. 
 
     
     
       2. The computing system of  claim 1 , wherein associating the first candidate advertisement image with the advertisement campaign comprises associating metadata with the first candidate advertisement image, and wherein the metadata comprises an advertisement campaign identifier of the advertisement campaign. 
     
     
       3. The computing system of  claim 1 , wherein the first candidate advertisement image is an image of a video advertisement. 
     
     
       4. The computing system of  claim 1 , wherein the color range threshold comprises an allowable color bit value variance. 
     
     
       5. The computing system of  claim 1 , wherein the set of acts further comprise:
 determining a histogram indicative of a distribution of the RGB pixel color values of the first candidate advertisement image, 
 outputting, to a display, the histogram, and 
 determining the first color value of the top color proportion for the first candidate advertisement image comprises determining, based on the histogram, the first color value of the top color proportion for the first candidate advertisement image. 
 
     
     
       6. The computing system of  claim 1 ,
 wherein the set of acts further comprise obtaining the color range threshold for the advertisement campaign from a thresholds data store, and 
 wherein the thresholds data store stores respective color range thresholds for respective advertisement campaigns. 
 
     
     
       7. The computing system of  claim 1 , wherein the set of acts further comprise identifying that the second candidate advertisement image and the first candidate advertisement image belong to the same advertisement campaign. 
     
     
       8. The computing system of  claim 7 , wherein the set of acts further comprise storing, in a database, an association between the second candidate advertisement image, the first candidate advertisement image, and the advertisement campaign. 
     
     
       9. The computing system of  claim 1 , wherein the set of acts further comprise storing, in a database, the association between the first candidate advertisement image and the advertisement campaign. 
     
     
       10. A method comprising:
 obtaining, by a computing system, a first candidate advertisement image and a second candidate advertisement image, different than the first candidate advertisement image; 
 determining, by the computing system, red green blue (RGB) pixel color values of the first candidate advertisement image and RGB pixel color values of the second candidate advertisement image,
 wherein the computing system analyzes a first plurality of pixels of the first candidate advertisement image to determine the RGB pixel color value for each pixel of the first plurality of pixels of the first candidate advertisement image and a second plurality of pixels of the second candidate advertisement image to determine the RGB pixel color value for each pixel of the second plurality of pixels; 
 
 determining, by the computing system based on the RGB pixel color values, a first color value of a top color proportion for the first candidate advertisement image and a second color value of a top color proportion for the second candidate advertisement image; 
 determining, by the computing system, that the first color value of the top color proportion for the first candidate advertisement image is within a color range threshold of a color value of a reference color proportion of an advertisement campaign; 
 determining that the second color value of the top color proportion for the second candidate advertisement image is within the color range threshold of the color value of the reference color proportion of the advertisement campaign; 
 based on determining that the first color value of the top color proportion for the first candidate advertisement image is within the color range threshold of the color value of reference color proportion, associating, by the computing system, the first candidate advertisement image with the advertisement campaign; and 
 based on determining that the second color value of the top color proportion for the second candidate advertisement image is within the color range threshold of the color value of reference color proportion, associating the second candidate advertisement image with the advertisement campaign. 
 
     
     
       11. The method of  claim 10 ,
 wherein associating the first candidate advertisement image with the advertisement campaign comprises associating metadata with the first candidate advertisement image, and 
 wherein the metadata comprises an advertisement campaign identifier of the advertisement campaign. 
 
     
     
       12. The method of  claim 10 , wherein the first candidate advertisement image is an image of a video advertisement. 
     
     
       13. The method of  claim 10 , wherein the color range threshold comprises an allowable color bit value variance. 
     
     
       14. The method of  claim 10 , further comprising:
 determining a histogram indicative of a distribution of the RGB pixel color values of the first candidate advertisement image, 
 wherein determining the first color value of the top color proportion for the first candidate advertisement image comprises determining, based on the histogram, the first color value of the top color proportion for the first candidate advertisement image. 
 
     
     
       15. The method of  claim 10 , further comprising:
 obtaining the color range threshold for the advertisement campaign from a thresholds data store, wherein the thresholds data store stores respective color range thresholds for respective advertisement campaigns. 
 
     
     
       16. A non-transitory computer-readable storage medium having stored therein instructions that when executed by a computing system cause the computing system to perform a set of acts comprising:
 obtaining, by the computing system, a first candidate advertisement image and a second candidate advertisement image, different than the first candidate advertisement image; 
 determining red green blue (RGB) pixel color values of the first candidate advertisement image and RGB pixel color values of the second candidate advertisement image, wherein the computing system analyzes a first plurality of pixels of the first candidate advertisement image to determine the RGB pixel color value for each pixel of the first plurality of pixels of the first candidate advertisement image and a second plurality of pixels of the second candidate advertisement image to determine the RGB pixel color value for each pixel of the second plurality of pixels; 
 determining, based on the RGB pixel color values, a first color value of a top color proportion for the first candidate advertisement image and a second color value of a top color proportion for the second candidate advertisement image; 
 determining that the first color value of the top color proportion for the first candidate advertisement image is within a color range threshold of a color value of a reference color proportion of an advertisement campaign; 
 determining that the second color value of the top color proportion for the second candidate advertisement image is within the color range threshold of the color value of the reference color proportion of the advertisement campaign;
 based on determining that the first color value of the top color proportion for the first candidate advertisement image is within the color range threshold of the color value of reference color proportion, associating the first candidate advertisement image with the advertisement campaign; and 
 based on determining that the second color value of the top color proportion for the second candidate advertisement image is within the color range threshold of the color value of reference color proportion, associating the second candidate advertisement image with the advertisement campaign. 
 
 
     
     
       17. The non-transitory computer-readable storage medium of  claim 16 ,
 wherein associating the first candidate advertisement image with the advertisement campaign comprises associating metadata with the first candidate advertisement image, and 
 wherein the metadata comprises an advertisement campaign identifier of the advertisement campaign. 
 
     
     
       18. The non-transitory computer-readable storage medium of  claim 16 , wherein the first candidate advertisement image is an image of a video advertisement. 
     
     
       19. The non-transitory computer-readable storage medium of  claim 16 , wherein the color range threshold comprises an allowable color bit value variance. 
     
     
       20. The non-transitory computer-readable storage medium of  claim 16 , wherein the set of acts further comprise:
 determining a histogram indicative of a distribution of the RGB pixel color values of the first candidate advertisement image, and 
 determining the first color value of the top color proportion for the first candidate advertisement image comprises determining, based on the histogram, the first color value of the top color proportion for the first candidate advertisement image.